Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4974 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.7334. Min Act: -0.0000

Data Index: 1396779 (Python Code)

Max Activating Token Index: 1012

Text #1

Max Range: 3.7334. Min Range: -3.7334

Max Act: 2.0860. Min Act: -0.0000

Data Index: 821337 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 3.7334. Min Range: -3.7334

Max Act: 2.1877. Min Act: -0.0000

Data Index: 130243 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 3.7334. Min Range: -3.7334

Max Act: 2.1221. Min Act: -0.0000

Data Index: 1000826 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 3.7334. Min Range: -3.7334

Max Act: 2.0101. Min Act: -0.0000

Data Index: 1165107 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 3.7334. Min Range: -3.7334

Max Act: 2.1248. Min Act: -0.0000

Data Index: 34361 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.9913. Min Act: -0.0000

Data Index: 1282388 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.9890. Min Act: -0.0000

Data Index: 970525 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 3.7334. Min Range: -3.7334

Max Act: 2.0370. Min Act: -0.0000

Data Index: 1437063 (Python Code)

Max Activating Token Index: 645

Text #9

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.7995. Min Act: -0.0000

Data Index: 424948 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.8906. Min Act: -0.0000

Data Index: 685529 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.8778. Min Act: -0.0000

Data Index: 138185 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.8815. Min Act: -0.0000

Data Index: 600193 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.8865. Min Act: -0.0000

Data Index: 1584771 (Python Code)

Max Activating Token Index: 884

Text #14

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.6611. Min Act: -0.0000

Data Index: 1078568 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.7247. Min Act: -0.0000

Data Index: 602600 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.7142. Min Act: -0.0000

Data Index: 322926 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.7051. Min Act: -0.0000

Data Index: 252785 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1395888 (Python Code)

Max Activating Token Index: 924

Text #19

Max Range: 3.7334. Min Range: -3.7334

Max Act: 1.6768. Min Act: -0.0000

Data Index: 1586956 (Python Code)

Max Activating Token Index: 895